The Agent Skills Directory

[SAFE]: The skill focuses on local code linting and formatting using the industry-standard swiftlint tool. It adheres to best practices by explicitly stating it does not silently install dependencies, upload user code, or store credentials.
[INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface as it processes Swift source code files (.swift) and configuration files (Package.swift, .swiftlint.yml). While malicious instructions could theoretically be embedded in comments within these files, the skill's capabilities are limited to executing a specific linter and reporting its output. It lacks high-privilege commands, network access, or sensitive file read/write operations that would be necessary to exploit an indirect injection, keeping the risk level at safe/low.

codeguard-swift